public void LexicalizedParserTest()
{
// GZIPed model in the file
var model = Files.Parser.Models("lexparser/englishPCFG.ser.gz");
using var fs = new FileStream(model, FileMode.Open);
using var isw = new ikvm.io.InputStreamWrapper(fs);
using var ois =
model.EndsWith(".gz")
? new ObjectInputStream(new GZIPInputStream(isw))
: new ObjectInputStream(isw);
var lp = LexicalizedParser.loadModel(ois);
Assert.NotNull(lp);
}
public static List <string> ExtractNounsFromSemantics(string sentence)
{
string assemblyPath = Assembly.GetExecutingAssembly().GetName().CodeBase;
string projectPath = Directory.GetParent(new Uri(Path.GetDirectoryName(Path.GetDirectoryName(Path.GetDirectoryName(assemblyPath)))).LocalPath).FullName;
string modelsDirectory = Path.GetFullPath(projectPath + @"\Parser\CoreNLP-3.9.1-Models\edu\stanford\nlp\models");
// Loading english PCFG parser from file
LexicalizedParser lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This shows loading and using an explicit tokenizer
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new java.io.StringReader(sentence);
var rawWords = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
sent2Reader.close();
var tree = lp.apply(rawWords);
return(tree.toArray().Cast <LabeledScoredTreeNode>().Where(n => n.isLeaf() && nounLabels.Contains(n.parent(tree).label().value())).Select(n => n.label().ToString()).ToList());
}
public TargetIdentificator(string word2VecModelPath)
{
lexParser = LexicalizedParser.loadModel(@"Resources\englishPCFG.ser.gz");
grammaticalStructureFactory = new PennTreebankLanguagePack().grammaticalStructureFactory();
lemmatizer = IStemmer.GetLemmatizer();
wordNetEngine = new WordNetEngine();
wordNetEngine.LoadFromDirectory(@"Resources\WordNet");
word2VecVocabulary = new Word2VecBinaryReader().Read(word2VecModelPath);
MLContext mlContext = new MLContext();
ITransformer mlModel = mlContext.Model.Load("MLModel.zip", out _);
predictionEngine = mlContext.Model.CreatePredictionEngine <ModelInput, ModelOutput>(mlModel);
wiki = new Wiki("NLP/1.0", "https://en.wikipedia.org", "https://en.wikipedia.org/w/api.php");
caching = new CachingFile();
}
public static void Start(string model, string fileName)
{
var grammar = (!String.IsNullOrEmpty(model)) ? model : Program.ParserModel;
var options = new[] { "-maxLength", "80", "-retainTmpSubcategories" };
var lp = LexicalizedParser.loadModel(grammar, options);
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var sentences = new List <ArrayList>();
if (!string.IsNullOrEmpty(fileName))
{
sentences.AddRange(new DocumentPreprocessor(fileName).Cast <ArrayList>());
}
else
{
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
var arrList = new ArrayList();
foreach (var s in sent)
{
arrList.Add(new Word(s));
}
sentences.Add(arrList);
const string Sent2 = "This is a slightly longer and more complex sentence requiring tokenization.";
var toke = tlp.getTokenizerFactory().getTokenizer(new StringReader(Sent2));
sentences.Add((ArrayList)toke.tokenize());
}
foreach (var sentence in sentences)
{
var parse = lp.apply(sentence);
parse.pennPrint();
System.Console.WriteLine("\n{0}\n", (parse.taggedYield()));
var gs = gsf.newGrammaticalStructure(parse);
var tdl = gs.typedDependenciesCCprocessed(true);
System.Console.WriteLine("{0}\n", tdl);
}
}
static void Main()
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var jarRoot = @"..\..\..\..\paket-files\nlp.stanford.edu\stanford-parser-full-2015-12-09\models\";
var modelsDirectory = jarRoot + @"\edu\stanford\nlp\models";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This sample shows parsing a list of correctly tokenized words
var sent = new[] { "This", "is", "an", "easy", "sentence", "." };
var rawWords = Sentence.toCoreLabelList(sent);
var tree = lp.apply(rawWords);
tree.pennPrint();
// This option shows loading and using an explicit tokenizer
var sent2 = "This is another sentence.";
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new StringReader(sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
sent2Reader.close();
var tree2 = lp.apply(rawWords2);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree2);
var tdl = gs.typedDependenciesCCprocessed();
Console.WriteLine("\n{0}\n", tdl);
// Extract collapsed dependencies from parsed tree
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(tree2);
}
//set up environment
//set up environment
public void Init()
{
// Path to models extracted from `stanford-parser-3.9.1-models.jar`
jarRoot = Path.Combine(Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location), "..\\..\\stanford-corenlp-full-2018-02-27");
modelsDirectory = jarRoot + "\\edu\\stanford\\nlp\\models";
// We should change current directory, so StanfordCoreNLP could find all the model files automatically
exeDir = Environment.CurrentDirectory;
//load json to create dictionary
try
{
string json = System.IO.File.ReadAllText(Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location) + "\\..\\..\\verbs-dictionaries.json");
JsonSerializer serializer = new JsonSerializer();
JArray values = JsonConvert.DeserializeObject <JArray>(json);
foreach (var item in values.Children())
{
dict.Add((string)item[0], (string)item[3]);
}
}
catch (Exception exp)
{
Console.WriteLine("Fail loading verb dictionary:\n {0}", exp);
}
// Loading english PCFG parser from file
try
{
lp = LexicalizedParser.loadModel(modelsDirectory + "\\lexparser\\englishPCFG.ser.gz");
}
catch (Exception exp)
{
Console.WriteLine("Fail loading parser model:\n{0}", exp);
}
Console.WriteLine("\nParser successfully loaded!\n");
}
public void SetUp()
{
var modelPath = Files.Parser.Models("lexparser/englishPCFG.ser.gz");
_lp = LexicalizedParser.loadModel(modelPath);
}
public void SentenceParser(string sent2)
{
var modelsDirectory = jarRoot + @"edu\stanford\nlp\models";
// Loading english PCFG parser from file
var lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This option shows loading and using an explicit tokenizer
sent2.ToLower();
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new java.io.StringReader(sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
sent2Reader.close();
var tree2 = lp.apply(rawWords2);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree2);
var tdl = gs.typedDependenciesCCprocessed();
//Console.WriteLine("\n{0}\n", tdl);
// Extract collapsed dependencies from parsed tree
var tp = new TreePrint("penn,typedDependenciesCollapsed");
tp.printTree(tree2);
ArrayList dep = gs.typedDependenciesCollapsed() as ArrayList;
foreach (TypedDependency td in dep)
{
for (int i = 0; i < keyword.Length; i++)
{
if (td.dep().originalText().Equals(keyword[i]))
{
keyFlag = true;
key = keyword[i];
break;
}
}
if (keyFlag)
{
break;
}
}
keyFlag = false;
switch (key)
{
case "circle":
Circle circle = new Circle();
shape = circle.GetProps();
propsUsed = Associator(shape, dep);
break;
case "rectangle":
Rectangle rect = new Rectangle();
shape = rect.GetProps();
propsUsed = Associator(shape, dep);
break;
case "triangle":
Triangle tri = new Triangle();
shape = tri.GetProps();
propsUsed = Associator(shape, dep);
break;
case "square":
Square square = new Square();
shape = square.GetProps();
propsUsed = Associator(shape, dep);
break;
default:
break;
} //End of Switch
dependency = tdl.ToString();
} //End of SentenceParser
// Constructors and finalizers:
private Repository()
{
_assemblyName = Regex.Match(_assemblyFullName, "^(.*?),.*$").Result("$1");
_rootDrive = ("/usr/project/xtmp/dp195/Poetix18/").Replace(@"\", Dsc);
_nlpFolder = ("rhetorica/nlp/").Replace(@"\", Dsc);
_openNlpModelsFolder = ("OpenNLP/models/").Replace(@"\", Dsc);
_openNlpModelsPath = RootDrive + _nlpFolder + _openNlpModelsFolder;
_wordNetFolder = ("WordNet_3/").Replace(@"\", Dsc);
_wordNetPath = RootDrive + _nlpFolder + _wordNetFolder;
_grammarFolder = ("StanfordParser/grammar/").Replace(@"\", Dsc);
_grammarPath = RootDrive + _nlpFolder + _grammarFolder;
_dataFolder = ("data/").Replace(@"\", Dsc);
_nlpTextsPath = RootDrive + _dataFolder;
string[] localTextDirectoryParts =
{
CurrentAssemblyDirectoryPath,
"..", "..","..", "data"
//"..", "..", "text"
};
_localTextPath = Path.Combine(localTextDirectoryParts) + "/"; // For development use
// WordNet engine:
Console.Write("Loading WordNet engine.... ");
_wordNetEngine = new WordNetEngine(WordNetPath, true);
Console.WriteLine("Done.");
// OpenNLP sentence detector:
Console.Write("Loading OpenNLP sentence detector.... ");
java.io.FileInputStream modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-sent.bin");
_sentenceModel = new SentenceModel(modelInputStream);
modelInputStream.close();
_sentenceDetector = new SentenceDetectorME(_sentenceModel);
Console.WriteLine("Done.");
// OpenNLP tokenizer:
Console.Write("Loading OpenNLP tokenizer.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-token.bin");
_tokenizerModel = new opennlp.tools.tokenize.TokenizerModel(modelInputStream);
modelInputStream.close();
_tokenizer = new opennlp.tools.tokenize.TokenizerME(_tokenizerModel);
Console.WriteLine("Done.");
// OpenNLP name finder:
Console.Write("Loading OpenNLP name finder.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-ner-person.bin");
_tokenNameFinderModel = new TokenNameFinderModel(modelInputStream);
modelInputStream.close();
_nameFinder = new NameFinderME(_tokenNameFinderModel);
Console.WriteLine("Done.");
// OpenNLP POS tagger:
Console.Write("Loading OpenNLP POS tagger.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-pos-maxent.bin");
_posModel = new POSModel(modelInputStream);
modelInputStream.close();
_tagger = new POSTaggerME(_posModel);
Console.WriteLine("Done.");
// OpenNLP chunker:
Console.Write("Loading OpenNLP chunker.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-chunker.bin");
_chunkerModel = new ChunkerModel(modelInputStream);
modelInputStream.close();
_chunker = new ChunkerME(_chunkerModel);
Console.WriteLine("Done.");
// OpenNLP parser:
if (_loadParser)
{
Console.Write("Loading OpenNLP parser.... ");
modelInputStream = new java.io.FileInputStream(OpenNlpModelsPath + "en-parser-chunking.bin");
_parserModel = new ParserModel(modelInputStream);
modelInputStream.close();
_parser = ParserFactory.create(_parserModel);
Console.WriteLine("Done.");
}
// Stanford parser:
//_stanfordParser = new LexicalizedParser(GrammarPath + "englishPCFG.ser.gz"); // Obsolete method
_stanfordParser = LexicalizedParser.loadModel(GrammarPath + "englishPCFG.ser.gz");
// Porter stemmer:
_porterStemmer = new PorterStemmer();
}
public string Tags(string input)
{
// Path to models extracted from `stanford-parser-3.6.0-models.jar`
var jarRoot = @"";
var modelsDirectory = jarRoot;
var lp = LexicalizedParser.loadModel(modelsDirectory + @"\lexparser\englishPCFG.ser.gz");
// This option shows loading and using an explicit tokenizer
var sent2 = input;
var tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(), "");
var sent2Reader = new java.io.StringReader(sent2);
var rawWords2 = tokenizerFactory.getTokenizer(sent2Reader).tokenize();
sent2Reader.close();
var tree2 = lp.apply(rawWords2);
// Extract dependencies from lexical tree
var tlp = new PennTreebankLanguagePack();
var gsf = tlp.grammaticalStructureFactory();
var gs = gsf.newGrammaticalStructure(tree2);
var tdl = gs.typedDependenciesCCprocessed();
// Extract collapsed dependencies from parsed tree
var tp = new TreePrint("penn,typedDependenciesCollapsed");
UnityEngine.Debug.Log(tdl);
//tp.printTree(tree2);
for (int i = 0; i < tdl.size(); i++)
{
TypedDependency node = (TypedDependency)tdl.get(i);
string relation = node.reln().getShortName();
if (relation.Contains("nsubj"))
{
IndexedWord act = node.gov();
//node.dep().getword()
action = act.value();
UnityEngine.Debug.Log("This is the action " + action);
IndexedWord subject = node.dep();
subj = subject.value();
UnityEngine.Debug.Log("This is the subject " + subj);
}
if (relation.Contains("dobj"))
{
IndexedWord act = node.gov();
//node.dep().getword()
action = act.value();
UnityEngine.Debug.Log("This is the action " + action);
IndexedWord tar = node.dep();
target = tar.value();
UnityEngine.Debug.Log("This is the target " + target);
}
if (relation.Contains("nmod"))
{
IndexedWord tar_two = node.dep();
second_target = tar_two.value();
UnityEngine.Debug.Log("This is the target second " + second_target);
}
}
return(tdl.ToString());
}
public edu.stanford.nlp.parser.lexparser.LexicalizedParser LoadLexicalizedParser(string jarLexicalizedParserFile)
{
return(LexicalizedParser.loadModel(jarLexicalizedParserFile));
}